Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    void

    np_max-act · gemini-2.0-flash

    This neuron responds to programming‐language definition keywords, i.e. tokens like “class” or the return‐type “void” that mark class and method declarations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    methods for managing resource cleanup and object disposal in code.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Ready
    -0.07
     installer
    -0.07
    Provider
    -0.06
    DAO
    -0.06
    -def
    -0.06
    :↵↵↵↵
    -0.06
     forming
    -0.06
    -Y
    -0.06
     turns
    -0.06
     accepted
    -0.06
    POSITIVE LOGITS
    alış
    0.08
    дн
    0.07
    __;
    0.07
    {{--
    0.06
    égorie
    0.06
    DX
    0.06
    ARRANT
    0.06
    @student
    0.06
    lds
    0.06
    .toBe
    0.06
    Act Density 0.013%

    No Known Activations